arXiv AI
Observe, Share, or Predict? Disentangling Partner Information in Embodied Multi-Agent Collaboration
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jun 29
LLawCo: Learning Laws of Cooperation for Modeling Embodied Multi-Agent Behavior
arXiv:2606. 28182v1 Announce Type: cross Abstract: Embodied agents operating in decentralized and partially observable environments have attracted growing attention in recent years.
arXiv AI
Oct 7
Partially Observable Zero-shot coordination by Predicting Intention of Partner
The paper introduces Predicting Intention of Partner (PIP), a method for zero‑shot coordination in partially observable settings. PIP employs a Joint‑view VAE to create a partner representation from local observations and uses Partner‑State Belief networks to infer hidden partner states from interaction history. Experiments on Burrito‑PO, Overcooked‑PO, and Melting Pot, along with human evaluation, show that PIP outperforms other methods and demonstrates effective coordination with unseen partners under occlusion.
arXiv AI
5d ago
Compositional RL: Evaluating and Training LLMs for Collaborative Reasoning
arXiv:2610.17456v1 Announce Type: cross Abstract: Language models are often evaluated alone but increasingly deployed together, routed between, made to debate, ensembled, or collaboratively trained....
arXiv AI
Jul 13
Embodied Multi-Agent Coordination by Aligning World Models Through Dialogue
arXiv:2605. 12920v3 Announce Type: replace-cross Abstract: Effective collaboration between embodied agents requires more than acting in a shared environment; it demands communication grounded in each agent's evolving understanding of the world.
arXiv AI
Jul 31
Partner Capability Estimation for Task-Agnostic Adaptation in Ad-Hoc Teamwork
arXiv:2607. 27177v1 Announce Type: new Abstract: Effective collaboration with novel and diverse partners is a crucial skill for autonomous agents.
arXiv AI
Oct 7
Attacca: Goal-Directed Control under State Continuity for Long-Horizon Embodied Agents
Attacca is a new approach for training visual goal‑conditioned policies that can handle continuous long‑horizon task execution in embodied agents. It decouples goal images from the execution environment by sampling class‑compatible masked goals from other worlds, enabling the policy to ground targets in the current view via a target‑mask prediction head. The method also introduces behavioral‑phase conditioning to distinguish Search, Approach, and Interact stages, and achieves significant performance gains on Minecraft tasks, outperforming baselines by up to 7× on long‑horizon scenarios.